| {"model": "codellama/CodeLlama-7b-Python-hf", "data_path": "/u3/ns3mathe/tdg/2_code_llama_finetuning/dataset_processing/data", "project_name": "ctllama7b", "train_split": "train", "valid_split": "validation", "text_column": "text", "lr": 2e-05, "epochs": 6, "batch_size": 3, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 4096, "use_peft": true, "lora_r": 32, "lora_alpha": 64, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 4096, "repo_id": "NobleMathews/ctllama7b", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null} |